Hamid Laga

Papers

Total Citations

H-Index

About

Hamid Laga is a prominent researcher whose work sits at the intersection of computer vision, 3D reconstruction, and deep learning, with a particular focus on extracting rich geometric information from visual data. His most impactful contribution is a comprehensive survey on deep learning-based depth estimation from monocular images and videos, which synthesizes over a decade of research spanning more than 500 publications — a testament to the field's rapid growth and the survey's value as a definitive reference, already accumulating 55 citations since its 2024 publication. This work addresses critical applications in autonomous driving, robotics, and digital entertainment, where understanding 3D structure from a single camera remains a fundamental challenge. Laga has also advanced joint depth and surface normal estimation through multi-stage information diffusion frameworks, pushing the boundaries of geometrically consistent scene understanding. His research further extends to 3D face reconstruction, where he explores reinforcement learning strategies to develop more label-efficient, robust models capable of handling occlusions and real-world noise — with direct implications for human-computer interaction and biometric systems. Collectively, his contributions reflect a sustained commitment to bridging theoretical deep learning advances with practical, high-impact visual computing applications.